Skeleton‐based human activity recognition for elderly monitoring systems

Abstract

There is a significantly increasing demand for monitoring systems for elderly people in the health-care sector. As the aging population increases, patient privacy violations and the cost of elderly assistance have driven the research community toward computer vision and image processing to design and deploy new systems for monitoring the elderly in the authors' society and turning their living houses into smart environments. By exploiting recent advances and the low cost of threedimensional (3D) depth sensors such as Microsoft Kinect, the authors propose a new skeleton-based approach to describe the spatio-temporal aspects of a human activity sequence, using the Minkowski and cosine distances between the 3D joints. We trained and validated their approach on the Microsoft MSR 3D Action and MSR Daily Activity 3D datasets using the Extremely Randomised Trees algorithm. The results are very promising, demonstrating that the trained model can be used to build a monitoring system for the elderly using open-source libraries and a low-cost depth sensor.

Human activity recognition using 2D skeleton data and supervised machine learning

“…This feature vector was then used as an input to the RF classifier for action classification [12]. The works given in [10–12] also use skeletal joints’ features for activity recognition as are used in the proposed method; however, the positions of skeletal joints are obtained by using a depth camera such as Kinect in each case. In our work, we extract skeletal joints’ positions directly from the video sequence without using any specific depth camera or device.…”

Human activity recognition with analysis of angles between skeletal joints using a RGB‐depth sensor

“…In [33] a new skeleton-based method is proposed to describe the spatio-temporal aspects of an activity data sequence via the Minkowski and cosine distances between 3D skeletal joints. In [34], multifeatures along with a hidden Markov model (HMM) are used with a single camera for a healthcare application.…”

“…In [37], graph formulation is employed for abnormal activity recognition. Although there are some RGB-based studies in the literature, the applications suffer in environments that are totally dark or where illumination changes are present, despite the use of a multi-camera system consisting of eight cameras installed to view a room from every possible angle and to overcome an issue with subject occlusion, for example [33]. However, unlike RGB-based methods, depth-based methods are invariant to illumination changes.…”

Insights on Research-based Approaches in Human Activity Recognition System

“…They validated their model for the superior performance as compared to the state of the artwork on four different public domain dataset that includes 1) MSRAction3D, 2) MSRDailyActivity3D, 3) MSRGesture3D and MSRActionPairs3D. One of the very recent works towards elderly monitoring system is considered for the in-depth study as well as a state of artwork for the further optimization as a contribution to this research problem domain is done by Hbali et al [34], where smart environment in the home is advocates for the aging people health care. In their work they have used 3-D depth sensors and proposed a method which is skeleton based and using Minkowski and Cosine distance for finding the accurate 3D joints.…”